{"title":"A Robust Fault Diagnosis Scheme using Deep Learning for High Voltage Transmission Line","authors":"Sazzed Mahamud Khan, A. Shatil","doi":"10.53799/ajse.v21i2.204","DOIUrl":"https://doi.org/10.53799/ajse.v21i2.204","url":null,"abstract":"The transmission lines repeatedly face an aggregation of shunt-faults and its impact in the real time system increases the vulnerability, damage in load, and line restoration cost. Fault detection in power transmission lines have become significantly crucial due to a rapid increase in number and length. Any kind of interruption or tripping in transmission lines can result in a massive failure over a large area, which necessitates the need of effective protection. The diagnosis of faults help in detecting and classifying transients that eventually make the protection of transmission lines convenient. In this paper, we propose a deep learning-enabled technique for the detection and classification of transmission line faults. The faulty information are extracted using Discrete Wavelet Transform (DWT) and fed into the multilayer perceptron classification model. The results indicate that the proposed approach is capable of accurately classifying and detecting faults in transmission line with high precision.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128010372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md. Ismail Hossen, Michael Goh, Tee Connie, Md. Nazmul Hossain
{"title":"An Approach to Recognize Vehicles Context Flow for Smartphone-Based Outdoor Parking Using Supervised Machine Learning Classifiers","authors":"Md. Ismail Hossen, Michael Goh, Tee Connie, Md. Nazmul Hossain","doi":"10.53799/ajse.v21i2.316","DOIUrl":"https://doi.org/10.53799/ajse.v21i2.316","url":null,"abstract":"Abstract— Finding an available parking space in outdoor environments such as university campuses and roadsides need a good parking system. In a general parking system, detecting a vehicle entering leaving the parking premise is one of the major steps. Currently, there are parking systems that use cameras or external sensors to detect the leaving and entering of the automobiles. External sensors-based systems require a costly sensor installation at each parking slot while the camera-based systems require sophisticated camera setup. Both parking systems need very high cost of deployment and maintenance. Besides, the additional need for network setup and hardware capacity increases the complexity that makes the system difficult to be implemented in an outdoor environment that typically involve a bigger coverage area. To encounter the issues, paper presents a parking system for outdoor parking systems using only smartphone-oriented sensors. The proposed approach does not require additional sensors installation nor manpower support. The proposed system takes the inputs from smartphones to detect the driver’s context that is used to recognize the flow of the vehicle. Context flow recognition indicates whether a driver is parking or unparking his/her vehicle. Supervised classifiers like support vector machines (SMV) and decision trees (DT) are used to recognize the parking or unparking actions to enable vehicles tracking in the parking area. Outcome of the proposed approach is a significant contribution for outdoor parking system as it solely utilizes the sensors embedded in smartphones to detect parking behaviors.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121209259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mahfujur Rahman, Madina Hasan, M. Billah, Rukaiya Jahan Sajuti
{"title":"Political Fake News Detection from Different News Source on Social Media using Machine Learning Techniques","authors":"Mahfujur Rahman, Madina Hasan, M. Billah, Rukaiya Jahan Sajuti","doi":"10.53799/ajse.v21i1.383","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.383","url":null,"abstract":"People are more dependable on online news systems than ever in this modern time and day. The more people depend on online news, magazines, and journals, the more likely it will have more significant consequences of fake news or rumors. In the era of social networking, it has become a significant problem that negatively influences society. The fact is that the internet has become more accessible than ever, and its uses have increased exponentially. From 2005 to 2020, overall web users have increased from 1.1 billion to 3.96 billion. As most individuals' primary sources are microblogging networks, fake news spreads faster than ever. Thus it has become very complicated to detect fake news over the internet. For that purpose, we have used four traditional machine learning (ML) algorithms and long short-term memory (LSTM) methods. The four traditional methods are as follows logistic regression (LR), decision tree (DT) classification, k-nearest neighbors (KNN) classification, and naive bayes (NB) classification. To conduct this experiment, we first implemented four traditional machine learning methods. Then we trained our dataset with LSTM and Bi-LSTM (bidirectional long-short term memory) to get the best-optimized result. This paper experimented with four traditional methods and two deep learning models to find the best models for detecting fake news. In our research, we can see that, from four traditional methods, logistic regression performs best and generate 96% accuracy, and the Bi-LSTM model can generate 99% accuracy, which outbreaks all previous scores.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126767719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Babu, M. Ahmmed, Mir Kaosar Ahamed, M. M. Rahman
{"title":"A Cluster Based Feasible Time Interval for Tracking Lost or Stolen Vehicle","authors":"M. Babu, M. Ahmmed, Mir Kaosar Ahamed, M. M. Rahman","doi":"10.53799/ajse.v21i1.201","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.201","url":null,"abstract":"The system for tracking and monitoring lost or stolen vehicle is challenging. This device is widely used to assess the vehicle's location using GPS technology. It can be used to track a vehicle or vehicle fleet and to obtain information about the vehicle's current location. There are various challenges for tracking and monitoring vehicles and finding lost vehicles due to the lack of proper real-time vehicle location and hence it is difficult to take necessary action in the immediate proper time after the vehicle has lost or stolen. In this paper a Cluster Based Feasible Time Interval for Vehicle Tracking (CFTVT) algorithm for measuring the minimum time interval for taking action after the vehicle has lost or stolen is proposed. This proposed model helps to imply any appropriate vehicle tracking algorithm in the exact proper time after the vehicle has been lost or stolen.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128755782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Highly Directive Graphene Based Hybrid Plasmonic Nanoantenna for Terahertz Applications","authors":"Richard Victor Biswas, Farhadur Arifin","doi":"10.53799/ajse.v21i1.290","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.290","url":null,"abstract":"To satisfy the necessity for elevated data transmission rates in 5G and beyond networks, terahertz band communication (0.1 - 10 THz) is envisaged as a crucial wireless technology. Two-dimensional graphene nanomaterial is being extensively integrated into the plasmonic antennas as it allows them to resonate in the terahertz wave spectrum. In this paper, a graphene-based hybrid terahertz plasmonic nano-scale antenna has been modelled to acquire a maximum gain and directivity of 8.1 dB and 8.23 dBi, respectively, by varying the conductivity of graphene via gate bias voltage. Moreover, a combination of several tailored radiating layers of silver, SiO2 and graphene sheets is arranged in the proposed nanoantenna in such a way that the return loss (S11) of -26.595 dB and a wider bandwidth of 1241.3 GHz are obtained. It is evident that the proposed graphene-based hybrid plasmonic nanoantenna could be considered as an ideal candidate for terahertz communication owing to its excellent radiation characteristics.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"355 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131544735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Mahmood, Rodionov Yuriy Viktorovich, Nikitin Dmitriy Vyacheslavovich, Voronin Nikolai Vladimirovich, Dmitriy Nikolayevich Protasov
{"title":"A Comprehensive Review of Liquid Ring Vacuum Pumps and Compressors for Improving Global Efficiency and Energy Saving","authors":"M. Mahmood, Rodionov Yuriy Viktorovich, Nikitin Dmitriy Vyacheslavovich, Voronin Nikolai Vladimirovich, Dmitriy Nikolayevich Protasov","doi":"10.53799/ajse.v21i1.272","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.272","url":null,"abstract":"Liquid ring vacuum pumps and compressors are mechanical positive displacement turbomachines that can operate in the mode of both vacuum compressor and vacuum pump. They are widely used in the fields of filtration, cryogenic, reaction, gas injection, condensation, evaporation, and convective drying. Despite their low performance, they have many advantages such as low costs, simplicity, reliability, improve suction characteristics, and in many cases, can provide a more efficient option. Improving efficiency is the key to decrease energy consumption and costs. The article analyzed and evaluated the previous investigations regarding these machines with a focus on challenges of improving efficiency, advances in numerical simulation, and experiments to afford beneficial insight on future research and next steps. The study revealed that the thermal interaction and the cavitation phenomenon are among the most important problems that require further research.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133772270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimal Design of Fractional Order PID Controllers for Solid Oxide Fuel Cell System Employing PSO Algorithm","authors":"Swati Singh, V. K. Tayal, H. P. Singh, V. Yadav","doi":"10.53799/ajse.v21i1.225","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.225","url":null,"abstract":"Solid Oxide Fuel Cells (SOFCs) are gaining attraction in order to facilitate various applications owing to portability, low pollution and high efficiency. However, due to strong nonlinearity, fast variations in loading conditions and sluggish dynamics, regulation of the output voltage of SOFCs is disturbed. This paper aims to enhance the dynamic performance of SOFC by employing PI, PI Fast, PIDF, 2-DOF PID and PSO optimized FO-PID controllers under uncertain input conditions. The PID tuner is used for tuning the PI, PI fast, PIDF and 2-DOF PID controller parameters. The PSO technique is utilized for optimizing of FO-PID controller. The SOFC output with various controllers is compared in terms of performance specifications such as peak overshoot, settling time, steady state error and rise time. The comparison of computer simulation results manifests that the proposed PSO-FOPID controller scheme yields in far better performance with SOFC subjected to uncertain input.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132055944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Risk Identification and Analysis in Software Development in Bangladesh IT Industry: A Hybrid Model","authors":"Tania Rahman, Shanto Kumar Saha, Md. Sajjadur Rahman Sohel, Md. Tamim Maula, Abhijit Bowmik, Rashidul Hasan Nabil","doi":"10.53799/ajse.v21i1.308","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.308","url":null,"abstract":"Software risk management is a critical and multi-stage process. All over the world, IT Industries face some threats during software risk management processes. Bangladesh is not exceptional. Our principal goal is to manage risk for Bangladesh's IT Industry. To gain a clear and transparent idea survey is the most effective way. And so, we arranged a survey questionnaire and collected data for risk impact areas on Bangladesh IT Industry. A workable and feasible risk management approach prompts an idea for the risk-mitigating plan. In any case, the high proportion of IT project failures demonstrates the futility of risk mitigation activities. From the survey, it is discovered that the most irritating obstructions behind software disappointment for the presence of covered-up and inconspicuous risks and lack of user communication, and lack of proper training on new technology which is overlooked in the greater part of the models. The proposed model works with the improvement of the risk mitigation plan through four phases, the DVC committee, and the NUT train-up team. Depending upon the survey replies added another unique feature called the NUT train-up team. The model considered all four phases of risk management, with the mitigation phase and training on new technologies receiving the greatest attention.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122793216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Emergency Distribution Network Design & Analysis for Consecrated COVID 19 Hospital Zone","authors":"A. Shatil, Lutfur Rahman","doi":"10.53799/ajse.v21i1.206","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.206","url":null,"abstract":"A power distribution network is always a key topic in a grid system because of more complexity. Rapidly or sudden load increasing to a particular one or two feeders can arise uncertainty and unbalance conditions in the system. Voltage fluctuations, Deviations, THD (total harmonic distortion), Reactive power imbalances can seriously unstable the grid for load increasing situations. In recent days due to COVID 19 condition, dedicated hospitals are connected to the distribution network. Because of its urgency and usefulness, a new type of distribution network called loop plus parallel has been presented in this paper. Finally, the simulation studies show better performance when comparing the traditional types of networks.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116867406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md. Rahimuddin, Md. Mizanur Rahman, Md. Shoriful Islam, M. A. Sattar, M. A. Halim, M. Haque, Md. Nazrul Islam Khan, Mst. Samia Tabassum
{"title":"Effect of N doping on the Optical and Electrical properties of Thermal Spray pyrolysed ZnO Thin Films","authors":"Md. Rahimuddin, Md. Mizanur Rahman, Md. Shoriful Islam, M. A. Sattar, M. A. Halim, M. Haque, Md. Nazrul Islam Khan, Mst. Samia Tabassum","doi":"10.53799/ajse.v21i1.315","DOIUrl":"https://doi.org/10.53799/ajse.v21i1.315","url":null,"abstract":"Nitrogen doped ZnO (ZnO:N), thin films have been deposited on glass substrate at the temperature of 350ºC by low cost homemade thermal spray pyrolysis (TSP) technique at a normal environmental conditions. In this study the average reflectance, transmittance and absorbance were measured (20%), (35%), and (45%), respectively. Absorption coefficient is 3.5x104cm-1 for N doped ZnO. Direct bandgap energy varies from 3.08-2.99eV and indirect band gap energy varies from 2.86-2.67eV for N doped ZnO. XRD analysis shows the (002) plane is present of samples and the average grain size decrease with increasing N concentration. Surface morphology of N doped ZnO films is studied by Scanning Electron Microscopy (SEM). It is seen that hexagonal crystal grains few voids are present for N doped ZnO samples. The surface exhibits more or less uniform surface morphology with some clusters on the whole surface. Hall Effect study confirms that Nitrogen doped ZnO (ZnO:N), thin films using Vander pauws method were made at room temperature at a constant field of 9.75 KG. Experimentally (1, 2, 3, and 4) % N doped ZnO thin films have shown in negative Hall Constant (RH). Which exhibited n-type characteristics. Hall Constant (RH), and Hall concentration (n), increases with increasing N doping concentration. Initially Hall mobility (μH), increases linearly for (1-2) % N doping concentration then it decreases for the rest of the doping concentration. We also found that the resistivity (ρ) decreases and the conductivity (s) increases with increasing N doping concentration which exhibits the semiconducting nature.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122754061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}